You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.
# 统计弹幕次数
def count_danmu ( ) :
# 打开TXT文件以读取数据
file_path = ' 弹幕.txt '
# 初始化一个空的文本字符串，用于累积所有文本数据
danmu_list = [ ]
with open ( file_path , ' r ' , encoding = ' utf-8 ' ) as file :
for line in file :
# 在这里处理每一行的数据
# 示例：
danmu_list . append ( line . strip ( ) )
# 使用Counter统计弹幕出现次数
danmu_counter = Counter ( danmu_list )
# 筛选与AI技术应用相关的弹幕
ai_danmu_counter = { k : v for k , v in danmu_counter . items ( ) if ' AI ' in k or ' 人工智能 ' in k }
# 将筛选后的弹幕转换为Counter对象
ai_danmu_counter = Counter ( ai_danmu_counter )
# 获取AI技术应用方面数量排名前8的弹幕
top_8_ai_danmus = ai_danmu_counter . most_common ( 8 )
# 打印排名前8的AI技术应用方面的弹幕及其出现次数
for idx , ( danmu , count ) in enumerate ( top_8_ai_danmus , 1 ) :
print ( f ' 排名 # { idx } : 弹幕 " { danmu } " 出现次数： { count } ' )
#top_76016_danmus = danmu_counter.most_common(76016)
# 将AI技术应用方面的统计数据写入Excel
df = pd . DataFrame ( list ( ai_danmu_counter . items ( ) ) , columns = [ ' 弹幕 ' , ' 次数 ' ] )
df . to_excel ( ' AI技术应用弹幕统计.xlsx ' , index = False )
